swarmclawai/swarmclaw

# Coding Agent

Delegate coding tasks to external coding agents via shell tools.

## Agent Execution Modes

### Claude Code (recommended)

Use `--print --permission-mode bypassPermissions` for non-interactive execution:

```bash
cd /path/to/project && claude --permission-mode bypassPermissions --print 'Your task here'
```

# GitHub Skill

Use the `gh` CLI to interact with GitHub repositories, issues, PRs, and CI.

## Setup

```bash
# Authenticate (one-time)
gh auth login

# Verify
gh auth status
```

# Google Workspace CLI

Use `gws` when the task is about Google Workspace resources or Google Workspace API automation.

Prefer `gws` over generic HTTP calls when possible because it already knows the Workspace API surface and returns structured JSON by default.

## Rules

1. Start with read/list/get commands before mutating Workspace state.
2. Confirm IDs first: document IDs, spreadsheet IDs, file IDs, message IDs, calendar IDs, space IDs.
3. Do not run interactive auth flows from an agent tool call. If auth is missing, report that `gws` needs to be configured in plugin settings or via a manual terminal login.
4. Keep commands machine-readable. Prefer JSON output and parse it instead of scraping human text.
5. For large list operations, limit the scope first, then page or filter.

# Nano Banana Pro (Gemini 3 Pro Image)

Use the bundled script to generate or edit images.

## Generate

```bash
uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png" --resolution 1K
```

## Edit (Single Image)

```bash
uv run {baseDir}/scripts/generate_image.py --prompt "edit instructions" --filename "output.png" -i "/path/in.png" --resolution 2K

# nano-pdf

Use `nano-pdf` to apply edits to a specific page in a PDF using a natural-language instruction.

## Quick Start

```bash
nano-pdf edit deck.pdf 1 "Change the title to 'Q3 Results' and fix the typo in the subtitle"
```

## Creating a New PDF

```bash
nano-pdf create output.pdf "Create a one-page summary of quarterly results with a header, bullet points, and a footer"

# OpenAI Image Gen

Generate images via the OpenAI Images API with an HTML gallery viewer.

## Run

Note: Image generation can take longer than typical timeouts. Set a higher timeout when running via shell (e.g., 300 seconds).

```bash
python3 {baseDir}/scripts/gen.py
```

## Useful Flags

# Resourceful Problem Solving

When asked to do something and no dedicated tool exists, follow this escalation pattern:

## 1. Check Skills

Use `use_skill` to search for a matching skill. Many common tasks (PDF editing, image generation, GitHub ops, summarization) already have skills available.

## 2. Search for a CLI Tool

If no skill matches, check whether a CLI tool exists:

```bash
which <tool>          # already installed?

# Skill Creator

Guidance for creating effective skills that extend SwarmClaw agent capabilities.

## About Skills

Skills are modular, self-contained packages that provide specialized knowledge, workflows, and tools. They transform a general-purpose agent into a specialized one equipped with procedural knowledge that no model can fully possess.

### What Skills Provide

1. Specialized workflows — multi-step procedures for specific domains
2. Tool integrations — instructions for working with specific file formats or APIs
3. Domain expertise — company-specific knowledge, schemas, business logic
4. Bundled resources — scripts, references, and assets for complex and repetitive tasks

# Summarize

Fast CLI to summarize URLs, local files, and YouTube links.

## Quick Start

```bash
summarize "https://example.com" --model google/gemini-3-flash-preview
summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto
```

## YouTube: Summary vs Transcript

# SwarmClaw Platform

SwarmClaw is an AI agent runtime and multi-agent orchestration platform. It gives agents a uniform set of tools, persistent memory, connector integrations, and the ability to delegate work to other agents.

Website: https://swarmclaw.ai
Docs: https://swarmclaw.ai/docs
GitHub: https://github.com/swarmclawai/swarmclaw
npm: `npm install -g swarmclaw`

## The 6 Primitive Tools

Every agent has access to these core tools. They cover the full range of agent capabilities.

| Tool | Purpose | When to Use |

# SwarmVault

Use when the agent has a SwarmVault MCP server enabled (transport `stdio`, command `npx -y @swarmvaultai/cli mcp`) pointed at a vault directory.

A SwarmVault workspace is a three-layer knowledge system:

- `raw/` — immutable source inputs (PDFs, transcripts, code, emails, URLs, sheets). Never edit.
- `wiki/` — generated markdown owned by the agent and the SwarmVault compiler. Pages carry frontmatter (`page_id`, `source_ids`, `node_ids`, `freshness`, `source_hashes`).
- `state/` — generated indexes, graphs, and approvals. Treat as opaque output of `compile`.

The vault contract lives in `swarmvault.schema.md` at the workspace root. The vault config lives in `swarmvault.config.json`.

## Rules

## Overview

SwarmClaw is a self-hosted AI agent orchestration platform. This skill gives you CLI access to manage agents, tasks, chats, chatrooms, goals, schedules, memory, wallets, connectors, autonomy controls, webhooks, extensions, and more across one or many SwarmClaw instances.

The CLI maps 1:1 to the SwarmClaw REST API. Every command follows the pattern:

```
swarmclaw <group> <action> [id] [--flags]
```

Install the CLI:

```bash
npm i -g @swarmclawai/swarmclaw